6 files changed, 89 insertions, 32 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 69d5190918e5..c52d1d48272a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -531,7 +531,7 @@ config CGROUP_DEVICE
 
 config CPUSETS
         bool "Cpuset support"
-        depends on SMP && CGROUPS
+        depends on CGROUPS
         help
           This option will let you create and manage CPUSETs which
           allow dynamically partitioning a system into sets of CPUs and
@@ -565,7 +565,7 @@ config CGROUP_MEM_RES_CTLR
         select MM_OWNER
         help
           Provides a memory resource controller that manages both anonymous
-          memory and page cache. (See Documentation/controllers/memory.txt)
+          memory and page cache. (See Documentation/cgroups/memory.txt)
 
           Note that setting this option increases fixed memory overhead
           associated with each page of memory in the system. By this,
@@ -597,6 +597,8 @@ config CGROUP_MEM_RES_CTLR_SWAP
           is disabled by boot option, this will be automatically disabled and
           there will be no overhead from this. Even when you set this config=y,
           if boot option "noswapaccount" is set, swap will not be accounted.
+          Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
+          size is 4096bytes, 512k per 1Gbytes of swap.
 
 endif # CGROUPS
 
@@ -687,7 +689,7 @@ config PID_NS
         depends on NAMESPACES && EXPERIMENTAL
         help
           Support process id namespaces.  This allows having multiple
-          process with the same pid as long as they are in different
+          processes with the same pid as long as they are in different
           pid namespaces.  This is a building block of containers.
 
           Unless you want to work with an experimental feature
@@ -952,7 +954,7 @@ config COMPAT_BRK
           Randomizing heap placement makes heap exploits harder, but it
           also breaks ancient binaries (including anything libc5 based).
           This option changes the bootup default to heap randomization
-          disabled, and can be overriden runtime by setting
+          disabled, and can be overridden at runtime by setting
           /proc/sys/kernel/randomize_va_space to 2.
 
           On non-ancient distros (post-2000 ones) N is usually a safe choice.
@@ -1012,6 +1014,20 @@ config MARKERS
 
 source "arch/Kconfig"
 
+config SLOW_WORK
+        default n
+        bool
+        help
+          The slow work thread pool provides a number of dynamically allocated
+          threads that can be used by the kernel to perform operations that
+          take a relatively long time.
+
+          An example of this would be CacheFiles doing a path lookup followed
+          by a series of mkdirs and a create call, all of which have to touch
+          disk.
+
+          See Documentation/slow-work.txt.
+
 endmenu         # General setup
 
 config HAVE_GENERIC_DMA_COHERENT
@@ -1026,7 +1042,6 @@ config SLABINFO
 
 config RT_MUTEXES
         boolean
-        select PLIST
 
 config BASE_SMALL
         int
@@ -1111,7 +1126,7 @@ config INIT_ALL_POSSIBLE
           cpu_possible_map, some of them chose to initialize cpu_possible_map
           with all 1s, and others with all 0s.  When they were centralised,
           it was better to provide this option than to break all the archs
-          and have several arch maintainers persuing me down dark alleys.
+          and have several arch maintainers pursuing me down dark alleys.
 
 config STOP_MACHINE
         bool
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 8d4ff5afc1d8..dd7ee5f203f3 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/initrd.h>
 #include <linux/async.h>
+#include <linux/fs_struct.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 9aa968d54329..f5b978a9bb92 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index 9bdddbcb3d6a..69aebbf8fd2d 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -1,5 +1,6 @@
 #include <linux/delay.h>
-#include <linux/raid/md.h>
+#include <linux/raid/md_u.h>
+#include <linux/raid/md_p.h>
 
 #include "do_mounts.h"
 
@@ -112,8 +113,6 @@ static int __init md_setup(char *str)
         return 1;
 }
 
-#define MdpMinorShift 6
-
 static void __init md_setup_drive(void)
 {
         int minor, i, ent, partitioned;
diff --git a/init/initramfs.c b/init/initramfs.c
index 7dcde7ea6603..80cd713f6cc5 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -5,6 +5,7 @@
 #include <linux/fcntl.h>
 #include <linux/delay.h>
 #include <linux/string.h>
+#include <linux/dirent.h>
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 
@@ -166,8 +167,6 @@ static __initdata char *victim;
 static __initdata unsigned count;
 static __initdata loff_t this_header, next_header;
 
-static __initdata int dry_run;
-
 static inline void __init eat(unsigned n)
 {
         victim += n;
@@ -229,10 +228,6 @@ static int __init do_header(void)
         parse_header(collected);
         next_header = this_header + N_ALIGN(name_len) + body_len;
         next_header = (next_header + 3) & ~3;
-        if (dry_run) {
-                read_into(name_buf, N_ALIGN(name_len), GotName);
-                return 0;
-        }
         state = SkipIt;
         if (name_len <= 0 || name_len > PATH_MAX)
                 return 0;
@@ -303,8 +298,6 @@ static int __init do_name(void)
                 free_hash();
                 return 0;
         }
-        if (dry_run)
-                return 0;
         clean_path(collected, mode);
         if (S_ISREG(mode)) {
                 int ml = maybe_link();
@@ -417,14 +410,13 @@ static unsigned my_inptr;   /* index of next byte to be processed in inbuf */
 
 #include <linux/decompress/generic.h>
 
-static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only)
+static char * __init unpack_to_rootfs(char *buf, unsigned len)
 {
         int written;
         decompress_fn decompress;
         const char *compress_name;
         static __initdata char msg_buf[64];
 
-        dry_run = check_only;
         header_buf = kmalloc(110, GFP_KERNEL);
         symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL);
         name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL);
@@ -523,26 +515,76 @@ skip:
         initrd_end = 0;
 }
 
+#define BUF_SIZE 1024
+static void __init clean_rootfs(void)
+{
+        int fd;
+        void *buf;
+        struct linux_dirent64 *dirp;
+        int count;
+
+        fd = sys_open("/", O_RDONLY, 0);
+        WARN_ON(fd < 0);
+        if (fd < 0)
+                return;
+        buf = kzalloc(BUF_SIZE, GFP_KERNEL);
+        WARN_ON(!buf);
+        if (!buf) {
+                sys_close(fd);
+                return;
+        }
+
+        dirp = buf;
+        count = sys_getdents64(fd, dirp, BUF_SIZE);
+        while (count > 0) {
+                while (count > 0) {
+                        struct stat st;
+                        int ret;
+
+                        ret = sys_newlstat(dirp->d_name, &st);
+                        WARN_ON_ONCE(ret);
+                        if (!ret) {
+                                if (S_ISDIR(st.st_mode))
+                                        sys_rmdir(dirp->d_name);
+                                else
+                                        sys_unlink(dirp->d_name);
+                        }
+
+                        count -= dirp->d_reclen;
+                        dirp = (void *)dirp + dirp->d_reclen;
+                }
+                dirp = buf;
+                memset(buf, 0, BUF_SIZE);
+                count = sys_getdents64(fd, dirp, BUF_SIZE);
+        }
+
+        sys_close(fd);
+        kfree(buf);
+}
+
 static int __init populate_rootfs(void)
 {
         char *err = unpack_to_rootfs(__initramfs_start,
-                         __initramfs_end - __initramfs_start, 0);
+                         __initramfs_end - __initramfs_start);
         if (err)
                 panic(err);     /* Failed to decompress INTERNAL initramfs */
         if (initrd_start) {
 #ifdef CONFIG_BLK_DEV_RAM
                 int fd;
-                printk(KERN_INFO "checking if image is initramfs...");
+                printk(KERN_INFO "checking if image is initramfs...\n");
                 err = unpack_to_rootfs((char *)initrd_start,
-                        initrd_end - initrd_start, 1);
+                        initrd_end - initrd_start);
                 if (!err) {
-                        printk(" it is\n");
-                        unpack_to_rootfs((char *)initrd_start,
-                                initrd_end - initrd_start, 0);
+                        printk(KERN_INFO "rootfs image is initramfs; unpacking...\n");
                         free_initrd();
                         return 0;
+                } else {
+                        clean_rootfs();
+                        unpack_to_rootfs(__initramfs_start,
+                                 __initramfs_end - __initramfs_start);
                 }
-                printk("it isn't (%s); looks like an initrd\n", err);
+                printk(KERN_INFO "rootfs image is not initramfs (%s)"
+                                "; looks like an initrd\n", err);
                 fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700);
                 if (fd >= 0) {
                         sys_write(fd, (char *)initrd_start,
@@ -553,7 +595,7 @@ static int __init populate_rootfs(void)
 #else
                 printk(KERN_INFO "Unpacking initramfs...");
                 err = unpack_to_rootfs((char *)initrd_start,
-                        initrd_end - initrd_start, 0);
+                        initrd_end - initrd_start);
                 if (err) {
                         printk(" failed!\n");
                         printk(KERN_EMERG "%s\n", err);
diff --git a/init/main.c b/init/main.c
index 20d784ab5ef8..3585f073d636 100644
--- a/init/main.c
+++ b/init/main.c
@@ -408,8 +408,7 @@ static void __init smp_init(void)
          * Set up the current CPU as possible to migrate to.
          * The other ones will be done by cpu_up/cpu_down()
          */
-        cpu = smp_processor_id();
-        cpu_set(cpu, cpu_active_map);
+        set_cpu_active(smp_processor_id(), true);
 
         /* FIXME: This should be done in userspace --RR */
         for_each_present_cpu(cpu) {
@@ -772,6 +771,7 @@ static void __init do_basic_setup(void)
 {
         rcu_init_sched(); /* needed by module_init stage. */
         init_workqueues();
+        cpuset_init_smp();
         usermodehelper_init();
         driver_init();
         init_irq_proc();
@@ -796,6 +796,7 @@ static void run_init_process(char *init_filename)
  * makes it inline to init() and it becomes part of init.text section
  */
 static noinline int init_post(void)
+        __releases(kernel_lock)
 {
         /* need to finish all async __init code before freeing the memory */
         async_synchronize_full();
@@ -844,7 +845,7 @@ static int __init kernel_init(void * unused)
         /*
          * init can run on any cpu.
          */
-        set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
+        set_cpus_allowed_ptr(current, cpu_all_mask);
         /*
          * Tell the world that we're going to be the grim
          * reaper of innocent orphaned children.
@@ -865,8 +866,6 @@ static int __init kernel_init(void * unused)
         smp_init();
         sched_init_smp();
 
-        cpuset_init_smp();
-
         do_basic_setup();
 
         /*